Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زاده
    -0.06
    ΑΛ
    -0.06
    Doc
    -0.06
    xsd
    -0.06
    わけ
    -0.06
    .Play
    -0.06
     sơ
    -0.06
     가입
    -0.06
    JSONArray
    -0.06
    意味
    -0.06
    POSITIVE LOGITS
     towing
    0.07
     slashing
    0.06
    Science
    0.06
    Quotes
    0.06
     měsí
    0.06
     tsunami
    0.06
     slate
    0.06
     pf
    0.06
     Unknown
    0.06
     Teacher
    0.06
    Act Density 0.032%

    No Known Activations